Upload folder using huggingface_hub

.gitattributes

@@ -57,3 +57,4 @@ llama3-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-gob-plan-122/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen2-gob-plan122-2epoch/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3-8b-os-plan-123/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+qwen3-8b-os-plan-124/tokenizer.json filter=lfs diff=lfs merge=lfs -text

qwen3-8b-os-plan-124/README.md

@@ -0,0 +1,78 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen3-8b-os-plan-124
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# qwen3-8b-os-plan-124
+
+This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Qwen3-8B](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Qwen3-8B) on the os-plan-124 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1949
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 32
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4571        | 0.2247 | 50   | 0.4386          |
+| 0.3406        | 0.4494 | 100  | 0.3288          |
+| 0.2888        | 0.6742 | 150  | 0.2573          |
+| 0.246         | 0.8989 | 200  | 0.2198          |
+| 0.1473        | 1.1213 | 250  | 0.2104          |
+| 0.1449        | 1.3461 | 300  | 0.1972          |
+| 0.1318        | 1.5708 | 350  | 0.1875          |
+| 0.1304        | 1.7955 | 400  | 0.1800          |
+| 0.1033        | 2.0180 | 450  | 0.1739          |
+| 0.0555        | 2.2427 | 500  | 0.1954          |
+| 0.059         | 2.4674 | 550  | 0.1922          |
+| 0.0581        | 2.6921 | 600  | 0.1944          |
+| 0.0616        | 2.9169 | 650  | 0.1949          |
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.2-rc0

qwen3-8b-os-plan-124/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

qwen3-8b-os-plan-124/all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1949300915002823,
+    "eval_runtime": 17.2465,
+    "eval_samples_per_second": 21.744,
+    "eval_steps_per_second": 2.725,
+    "total_flos": 75789046251520.0,
+    "train_loss": 0.2089029460120807,
+    "train_runtime": 4570.3932,
+    "train_samples_per_second": 4.674,
+    "train_steps_per_second": 0.146
+}

qwen3-8b-os-plan-124/chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

qwen3-8b-os-plan-124/config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

qwen3-8b-os-plan-124/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.1949300915002823,
+    "eval_runtime": 17.2465,
+    "eval_samples_per_second": 21.744,
+    "eval_steps_per_second": 2.725
+}

qwen3-8b-os-plan-124/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.1"
+}

qwen3-8b-os-plan-124/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d242c350bbc420a50140abb3fcec9e5e6a2bac1a1d0ad904b7a82881412c3dbe
+size 4902257696

qwen3-8b-os-plan-124/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362976ebd9db5e83e367823efa57461e26ed054545cf9dc348e7b7ac683b5d1c
+size 4915960368

qwen3-8b-os-plan-124/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21e04b33ae67c1675d6e842f6aa195bd856df4de14f662fc9cbb539b6f473b05
+size 4983068496

qwen3-8b-os-plan-124/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25777a634256feeec8a7fe89dc27970fc98f3cd38cb5a3e88cdc62d266a0dae
+size 1580230264

qwen3-8b-os-plan-124/model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

qwen3-8b-os-plan-124/runs/Jan24_20-17-14_hgx003/events.out.tfevents.1769257189.hgx003.3068347.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c71827746b9a709a9d5d04c8a7411b3b6ecee27cc7d36ff8895fea485518067c
+size 24176

qwen3-8b-os-plan-124/runs/Jan24_20-17-14_hgx003/events.out.tfevents.1769261800.hgx003.3068347.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0a822262f6369b015ebb3f4883e342b53b62362741b6d1003ff5638011c0ca5
+size 359

qwen3-8b-os-plan-124/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

qwen3-8b-os-plan-124/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

qwen3-8b-os-plan-124/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

qwen3-8b-os-plan-124/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 75789046251520.0,
+    "train_loss": 0.2089029460120807,
+    "train_runtime": 4570.3932,
+    "train_samples_per_second": 4.674,
+    "train_steps_per_second": 0.146
+}

qwen3-8b-os-plan-124/trainer_log.jsonl

@@ -0,0 +1,80 @@
+{"current_steps": 10, "total_steps": 669, "loss": 1.6977, "lr": 1.3432835820895524e-06, "epoch": 0.0449438202247191, "percentage": 1.49, "elapsed_time": "0:01:04", "remaining_time": "1:11:16"}
+{"current_steps": 20, "total_steps": 669, "loss": 1.0622, "lr": 2.835820895522388e-06, "epoch": 0.0898876404494382, "percentage": 2.99, "elapsed_time": "0:02:07", "remaining_time": "1:08:56"}
+{"current_steps": 30, "total_steps": 669, "loss": 0.6839, "lr": 4.3283582089552236e-06, "epoch": 0.1348314606741573, "percentage": 4.48, "elapsed_time": "0:03:07", "remaining_time": "1:06:31"}
+{"current_steps": 40, "total_steps": 669, "loss": 0.5266, "lr": 5.820895522388061e-06, "epoch": 0.1797752808988764, "percentage": 5.98, "elapsed_time": "0:04:07", "remaining_time": "1:04:46"}
+{"current_steps": 50, "total_steps": 669, "loss": 0.4571, "lr": 7.313432835820896e-06, "epoch": 0.2247191011235955, "percentage": 7.47, "elapsed_time": "0:05:14", "remaining_time": "1:04:49"}
+{"current_steps": 50, "total_steps": 669, "eval_loss": 0.4385504126548767, "epoch": 0.2247191011235955, "percentage": 7.47, "elapsed_time": "0:05:32", "remaining_time": "1:08:33"}
+{"current_steps": 60, "total_steps": 669, "loss": 0.4199, "lr": 8.805970149253732e-06, "epoch": 0.2696629213483146, "percentage": 8.97, "elapsed_time": "0:06:35", "remaining_time": "1:06:49"}
+{"current_steps": 70, "total_steps": 669, "loss": 0.3872, "lr": 9.999727665400876e-06, "epoch": 0.3146067415730337, "percentage": 10.46, "elapsed_time": "0:07:36", "remaining_time": "1:05:02"}
+{"current_steps": 80, "total_steps": 669, "loss": 0.384, "lr": 9.990199069047216e-06, "epoch": 0.3595505617977528, "percentage": 11.96, "elapsed_time": "0:08:36", "remaining_time": "1:03:25"}
+{"current_steps": 90, "total_steps": 669, "loss": 0.3541, "lr": 9.967083394667763e-06, "epoch": 0.4044943820224719, "percentage": 13.45, "elapsed_time": "0:09:36", "remaining_time": "1:01:47"}
+{"current_steps": 100, "total_steps": 669, "loss": 0.3406, "lr": 9.93044358052752e-06, "epoch": 0.449438202247191, "percentage": 14.95, "elapsed_time": "0:10:43", "remaining_time": "1:01:04"}
+{"current_steps": 100, "total_steps": 669, "eval_loss": 0.32883039116859436, "epoch": 0.449438202247191, "percentage": 14.95, "elapsed_time": "0:11:01", "remaining_time": "1:02:43"}
+{"current_steps": 110, "total_steps": 669, "loss": 0.305, "lr": 9.880379387779637e-06, "epoch": 0.4943820224719101, "percentage": 16.44, "elapsed_time": "0:12:08", "remaining_time": "1:01:42"}
+{"current_steps": 120, "total_steps": 669, "loss": 0.3243, "lr": 9.817027128840462e-06, "epoch": 0.5393258426966292, "percentage": 17.94, "elapsed_time": "0:13:13", "remaining_time": "1:00:30"}
+{"current_steps": 130, "total_steps": 669, "loss": 0.2935, "lr": 9.740559296244543e-06, "epoch": 0.5842696629213483, "percentage": 19.43, "elapsed_time": "0:14:13", "remaining_time": "0:59:00"}
+{"current_steps": 140, "total_steps": 669, "loss": 0.2785, "lr": 9.651184092990109e-06, "epoch": 0.6292134831460674, "percentage": 20.93, "elapsed_time": "0:15:12", "remaining_time": "0:57:29"}
+{"current_steps": 150, "total_steps": 669, "loss": 0.2888, "lr": 9.5491448656538e-06, "epoch": 0.6741573033707865, "percentage": 22.42, "elapsed_time": "0:16:18", "remaining_time": "0:56:27"}
+{"current_steps": 150, "total_steps": 669, "eval_loss": 0.2572707235813141, "epoch": 0.6741573033707865, "percentage": 22.42, "elapsed_time": "0:16:36", "remaining_time": "0:57:28"}
+{"current_steps": 160, "total_steps": 669, "loss": 0.2505, "lr": 9.434719441818106e-06, "epoch": 0.7191011235955056, "percentage": 23.92, "elapsed_time": "0:17:35", "remaining_time": "0:55:57"}
+{"current_steps": 170, "total_steps": 669, "loss": 0.2499, "lr": 9.308219373615574e-06, "epoch": 0.7640449438202247, "percentage": 25.41, "elapsed_time": "0:18:44", "remaining_time": "0:55:00"}
+{"current_steps": 180, "total_steps": 669, "loss": 0.2488, "lr": 9.16998908944939e-06, "epoch": 0.8089887640449438, "percentage": 26.91, "elapsed_time": "0:19:43", "remaining_time": "0:53:35"}
+{"current_steps": 190, "total_steps": 669, "loss": 0.2431, "lr": 9.020404956200016e-06, "epoch": 0.8539325842696629, "percentage": 28.4, "elapsed_time": "0:20:53", "remaining_time": "0:52:40"}
+{"current_steps": 200, "total_steps": 669, "loss": 0.246, "lr": 8.85987425447124e-06, "epoch": 0.898876404494382, "percentage": 29.9, "elapsed_time": "0:21:55", "remaining_time": "0:51:24"}
+{"current_steps": 200, "total_steps": 669, "eval_loss": 0.21981053054332733, "epoch": 0.898876404494382, "percentage": 29.9, "elapsed_time": "0:22:12", "remaining_time": "0:52:05"}
+{"current_steps": 210, "total_steps": 669, "loss": 0.2246, "lr": 8.688834069665819e-06, "epoch": 0.9438202247191011, "percentage": 31.39, "elapsed_time": "0:23:13", "remaining_time": "0:50:46"}
+{"current_steps": 220, "total_steps": 669, "loss": 0.2306, "lr": 8.50775010191001e-06, "epoch": 0.9887640449438202, "percentage": 32.88, "elapsed_time": "0:24:15", "remaining_time": "0:49:29"}
+{"current_steps": 230, "total_steps": 669, "loss": 0.1756, "lr": 8.317115398067289e-06, "epoch": 1.0314606741573034, "percentage": 34.38, "elapsed_time": "0:25:15", "remaining_time": "0:48:12"}
+{"current_steps": 240, "total_steps": 669, "loss": 0.1532, "lr": 8.117449009293668e-06, "epoch": 1.0764044943820226, "percentage": 35.87, "elapsed_time": "0:26:14", "remaining_time": "0:46:55"}
+{"current_steps": 250, "total_steps": 669, "loss": 0.1473, "lr": 7.909294577789765e-06, "epoch": 1.1213483146067416, "percentage": 37.37, "elapsed_time": "0:27:17", "remaining_time": "0:45:43"}
+{"current_steps": 250, "total_steps": 669, "eval_loss": 0.21036630868911743, "epoch": 1.1213483146067416, "percentage": 37.37, "elapsed_time": "0:27:34", "remaining_time": "0:46:12"}
+{"current_steps": 260, "total_steps": 669, "loss": 0.1475, "lr": 7.693218856597515e-06, "epoch": 1.1662921348314608, "percentage": 38.86, "elapsed_time": "0:28:40", "remaining_time": "0:45:06"}
+{"current_steps": 270, "total_steps": 669, "loss": 0.1483, "lr": 7.469810166471802e-06, "epoch": 1.2112359550561798, "percentage": 40.36, "elapsed_time": "0:29:41", "remaining_time": "0:43:53"}
+{"current_steps": 280, "total_steps": 669, "loss": 0.1511, "lr": 7.239676794028526e-06, "epoch": 1.256179775280899, "percentage": 41.85, "elapsed_time": "0:30:40", "remaining_time": "0:42:36"}
+{"current_steps": 290, "total_steps": 669, "loss": 0.1419, "lr": 7.003445335530572e-06, "epoch": 1.301123595505618, "percentage": 43.35, "elapsed_time": "0:31:42", "remaining_time": "0:41:26"}
+{"current_steps": 300, "total_steps": 669, "loss": 0.1449, "lr": 6.761758990821143e-06, "epoch": 1.346067415730337, "percentage": 44.84, "elapsed_time": "0:32:41", "remaining_time": "0:40:13"}
+{"current_steps": 300, "total_steps": 669, "eval_loss": 0.19717492163181305, "epoch": 1.346067415730337, "percentage": 44.84, "elapsed_time": "0:32:59", "remaining_time": "0:40:34"}
+{"current_steps": 310, "total_steps": 669, "loss": 0.1463, "lr": 6.515275812049644e-06, "epoch": 1.3910112359550562, "percentage": 46.34, "elapsed_time": "0:34:02", "remaining_time": "0:39:25"}
+{"current_steps": 320, "total_steps": 669, "loss": 0.1405, "lr": 6.264666911958404e-06, "epoch": 1.4359550561797754, "percentage": 47.83, "elapsed_time": "0:35:02", "remaining_time": "0:38:12"}
+{"current_steps": 330, "total_steps": 669, "loss": 0.1433, "lr": 6.0106146366086514e-06, "epoch": 1.4808988764044944, "percentage": 49.33, "elapsed_time": "0:36:10", "remaining_time": "0:37:10"}
+{"current_steps": 340, "total_steps": 669, "loss": 0.1403, "lr": 5.753810707520918e-06, "epoch": 1.5258426966292133, "percentage": 50.82, "elapsed_time": "0:37:13", "remaining_time": "0:36:00"}
+{"current_steps": 350, "total_steps": 669, "loss": 0.1318, "lr": 5.494954338288404e-06, "epoch": 1.5707865168539326, "percentage": 52.32, "elapsed_time": "0:38:12", "remaining_time": "0:34:49"}
+{"current_steps": 350, "total_steps": 669, "eval_loss": 0.18746493756771088, "epoch": 1.5707865168539326, "percentage": 52.32, "elapsed_time": "0:38:30", "remaining_time": "0:35:05"}
+{"current_steps": 360, "total_steps": 669, "loss": 0.1347, "lr": 5.234750330791268e-06, "epoch": 1.6157303370786518, "percentage": 53.81, "elapsed_time": "0:39:35", "remaining_time": "0:33:58"}
+{"current_steps": 370, "total_steps": 669, "loss": 0.1371, "lr": 4.973907156195405e-06, "epoch": 1.6606741573033708, "percentage": 55.31, "elapsed_time": "0:40:35", "remaining_time": "0:32:48"}
+{"current_steps": 380, "total_steps": 669, "loss": 0.1349, "lr": 4.713135025960652e-06, "epoch": 1.7056179775280897, "percentage": 56.8, "elapsed_time": "0:41:35", "remaining_time": "0:31:37"}
+{"current_steps": 390, "total_steps": 669, "loss": 0.1405, "lr": 4.4531439581106295e-06, "epoch": 1.750561797752809, "percentage": 58.3, "elapsed_time": "0:42:35", "remaining_time": "0:30:28"}
+{"current_steps": 400, "total_steps": 669, "loss": 0.1304, "lr": 4.194641844029227e-06, "epoch": 1.7955056179775282, "percentage": 59.79, "elapsed_time": "0:43:37", "remaining_time": "0:29:20"}
+{"current_steps": 400, "total_steps": 669, "eval_loss": 0.17997325956821442, "epoch": 1.7955056179775282, "percentage": 59.79, "elapsed_time": "0:43:54", "remaining_time": "0:29:31"}
+{"current_steps": 410, "total_steps": 669, "loss": 0.1346, "lr": 3.938332521047434e-06, "epoch": 1.8404494382022472, "percentage": 61.29, "elapsed_time": "0:45:11", "remaining_time": "0:28:32"}
+{"current_steps": 420, "total_steps": 669, "loss": 0.1234, "lr": 3.6849138560683305e-06, "epoch": 1.8853932584269661, "percentage": 62.78, "elapsed_time": "0:46:14", "remaining_time": "0:27:24"}
+{"current_steps": 430, "total_steps": 669, "loss": 0.1222, "lr": 3.435075845448105e-06, "epoch": 1.9303370786516854, "percentage": 64.28, "elapsed_time": "0:47:15", "remaining_time": "0:26:15"}
+{"current_steps": 440, "total_steps": 669, "loss": 0.1322, "lr": 3.189498736306584e-06, "epoch": 1.9752808988764046, "percentage": 65.77, "elapsed_time": "0:48:28", "remaining_time": "0:25:13"}
+{"current_steps": 450, "total_steps": 669, "loss": 0.1033, "lr": 2.948851174382565e-06, "epoch": 2.0179775280898875, "percentage": 67.26, "elapsed_time": "0:49:28", "remaining_time": "0:24:04"}
+{"current_steps": 450, "total_steps": 669, "eval_loss": 0.173874631524086, "epoch": 2.0179775280898875, "percentage": 67.26, "elapsed_time": "0:49:46", "remaining_time": "0:24:13"}
+{"current_steps": 460, "total_steps": 669, "loss": 0.065, "lr": 2.7137883834768076e-06, "epoch": 2.0629213483146067, "percentage": 68.76, "elapsed_time": "0:50:53", "remaining_time": "0:23:07"}
+{"current_steps": 470, "total_steps": 669, "loss": 0.0664, "lr": 2.4849503814396624e-06, "epoch": 2.107865168539326, "percentage": 70.25, "elapsed_time": "0:52:00", "remaining_time": "0:22:01"}
+{"current_steps": 480, "total_steps": 669, "loss": 0.0584, "lr": 2.2629602375607373e-06, "epoch": 2.152808988764045, "percentage": 71.75, "elapsed_time": "0:53:10", "remaining_time": "0:20:56"}
+{"current_steps": 490, "total_steps": 669, "loss": 0.0603, "lr": 2.048422376105299e-06, "epoch": 2.197752808988764, "percentage": 73.24, "elapsed_time": "0:54:14", "remaining_time": "0:19:48"}
+{"current_steps": 500, "total_steps": 669, "loss": 0.0555, "lr": 1.8419209306164653e-06, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "0:55:15", "remaining_time": "0:18:40"}
+{"current_steps": 500, "total_steps": 669, "eval_loss": 0.19535784423351288, "epoch": 2.242696629213483, "percentage": 74.74, "elapsed_time": "0:55:33", "remaining_time": "0:18:46"}
+{"current_steps": 510, "total_steps": 669, "loss": 0.0554, "lr": 1.6440181534640277e-06, "epoch": 2.2876404494382023, "percentage": 76.23, "elapsed_time": "0:57:43", "remaining_time": "0:17:59"}
+{"current_steps": 520, "total_steps": 669, "loss": 0.0608, "lr": 1.4552528849702852e-06, "epoch": 2.3325842696629215, "percentage": 77.73, "elapsed_time": "0:58:48", "remaining_time": "0:16:51"}
+{"current_steps": 530, "total_steps": 669, "loss": 0.061, "lr": 1.2761390862810907e-06, "epoch": 2.3775280898876403, "percentage": 79.22, "elapsed_time": "0:59:49", "remaining_time": "0:15:41"}
+{"current_steps": 540, "total_steps": 669, "loss": 0.0601, "lr": 1.107164439976764e-06, "epoch": 2.4224719101123595, "percentage": 80.72, "elapsed_time": "1:00:49", "remaining_time": "0:14:31"}
+{"current_steps": 550, "total_steps": 669, "loss": 0.059, "lr": 9.487890222330137e-07, "epoch": 2.4674157303370787, "percentage": 82.21, "elapsed_time": "1:01:50", "remaining_time": "0:13:22"}
+{"current_steps": 550, "total_steps": 669, "eval_loss": 0.1922154724597931, "epoch": 2.4674157303370787, "percentage": 82.21, "elapsed_time": "1:02:08", "remaining_time": "0:13:26"}
+{"current_steps": 560, "total_steps": 669, "loss": 0.0545, "lr": 8.014440501472909e-07, "epoch": 2.512359550561798, "percentage": 83.71, "elapsed_time": "1:03:16", "remaining_time": "0:12:19"}
+{"current_steps": 570, "total_steps": 669, "loss": 0.0627, "lr": 6.655307076412637e-07, "epoch": 2.5573033707865167, "percentage": 85.2, "elapsed_time": "1:04:16", "remaining_time": "0:11:09"}
+{"current_steps": 580, "total_steps": 669, "loss": 0.0609, "lr": 5.414190531362162e-07, "epoch": 2.602247191011236, "percentage": 86.7, "elapsed_time": "1:05:19", "remaining_time": "0:10:01"}
+{"current_steps": 590, "total_steps": 669, "loss": 0.0516, "lr": 4.29447011975474e-07, "epoch": 2.647191011235955, "percentage": 88.19, "elapsed_time": "1:06:18", "remaining_time": "0:08:52"}
+{"current_steps": 600, "total_steps": 669, "loss": 0.0581, "lr": 3.299194563372604e-07, "epoch": 2.692134831460674, "percentage": 89.69, "elapsed_time": "1:07:20", "remaining_time": "0:07:44"}
+{"current_steps": 600, "total_steps": 669, "eval_loss": 0.19437935948371887, "epoch": 2.692134831460674, "percentage": 89.69, "elapsed_time": "1:07:37", "remaining_time": "0:07:46"}
+{"current_steps": 610, "total_steps": 669, "loss": 0.0573, "lr": 2.431073751431529e-07, "epoch": 2.737078651685393, "percentage": 91.18, "elapsed_time": "1:08:36", "remaining_time": "0:06:38"}
+{"current_steps": 620, "total_steps": 669, "loss": 0.0494, "lr": 1.6924713622225975e-07, "epoch": 2.7820224719101123, "percentage": 92.68, "elapsed_time": "1:09:45", "remaining_time": "0:05:30"}
+{"current_steps": 630, "total_steps": 669, "loss": 0.0528, "lr": 1.0853984274007246e-07, "epoch": 2.8269662921348315, "percentage": 94.17, "elapsed_time": "1:10:43", "remaining_time": "0:04:22"}
+{"current_steps": 640, "total_steps": 669, "loss": 0.0549, "lr": 6.115078564427946e-08, "epoch": 2.8719101123595507, "percentage": 95.67, "elapsed_time": "1:11:45", "remaining_time": "0:03:15"}
+{"current_steps": 650, "total_steps": 669, "loss": 0.0616, "lr": 2.7208993618390578e-08, "epoch": 2.9168539325842695, "percentage": 97.16, "elapsed_time": "1:12:46", "remaining_time": "0:02:07"}
+{"current_steps": 650, "total_steps": 669, "eval_loss": 0.19488400220870972, "epoch": 2.9168539325842695, "percentage": 97.16, "elapsed_time": "1:13:04", "remaining_time": "0:02:08"}
+{"current_steps": 660, "total_steps": 669, "loss": 0.0499, "lr": 6.806881768539053e-09, "epoch": 2.9617977528089887, "percentage": 98.65, "elapsed_time": "1:14:09", "remaining_time": "0:01:00"}
+{"current_steps": 669, "total_steps": 669, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:16:10", "remaining_time": "0:00:00"}

qwen3-8b-os-plan-124/trainer_state.json

@@ -0,0 +1,609 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 50,
+  "global_step": 669,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0449438202247191,
+      "grad_norm": 23.779281058592794,
+      "learning_rate": 1.3432835820895524e-06,
+      "loss": 1.6977,
+      "step": 10
+    },
+    {
+      "epoch": 0.0898876404494382,
+      "grad_norm": 5.2036497982266425,
+      "learning_rate": 2.835820895522388e-06,
+      "loss": 1.0622,
+      "step": 20
+    },
+    {
+      "epoch": 0.1348314606741573,
+      "grad_norm": 2.568600438697201,
+      "learning_rate": 4.3283582089552236e-06,
+      "loss": 0.6839,
+      "step": 30
+    },
+    {
+      "epoch": 0.1797752808988764,
+      "grad_norm": 2.1204491601286954,
+      "learning_rate": 5.820895522388061e-06,
+      "loss": 0.5266,
+      "step": 40
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 1.9874912269535547,
+      "learning_rate": 7.313432835820896e-06,
+      "loss": 0.4571,
+      "step": 50
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "eval_loss": 0.4385504126548767,
+      "eval_runtime": 18.0437,
+      "eval_samples_per_second": 20.783,
+      "eval_steps_per_second": 2.605,
+      "step": 50
+    },
+    {
+      "epoch": 0.2696629213483146,
+      "grad_norm": 1.739900812069461,
+      "learning_rate": 8.805970149253732e-06,
+      "loss": 0.4199,
+      "step": 60
+    },
+    {
+      "epoch": 0.3146067415730337,
+      "grad_norm": 1.7912639502646979,
+      "learning_rate": 9.999727665400876e-06,
+      "loss": 0.3872,
+      "step": 70
+    },
+    {
+      "epoch": 0.3595505617977528,
+      "grad_norm": 2.022509681604849,
+      "learning_rate": 9.990199069047216e-06,
+      "loss": 0.384,
+      "step": 80
+    },
+    {
+      "epoch": 0.4044943820224719,
+      "grad_norm": 1.7985691117109854,
+      "learning_rate": 9.967083394667763e-06,
+      "loss": 0.3541,
+      "step": 90
+    },
+    {
+      "epoch": 0.449438202247191,
+      "grad_norm": 1.7471084051994163,
+      "learning_rate": 9.93044358052752e-06,
+      "loss": 0.3406,
+      "step": 100
+    },
+    {
+      "epoch": 0.449438202247191,
+      "eval_loss": 0.32883039116859436,
+      "eval_runtime": 17.4518,
+      "eval_samples_per_second": 21.488,
+      "eval_steps_per_second": 2.693,
+      "step": 100
+    },
+    {
+      "epoch": 0.4943820224719101,
+      "grad_norm": 1.5616721438545853,
+      "learning_rate": 9.880379387779637e-06,
+      "loss": 0.305,
+      "step": 110
+    },
+    {
+      "epoch": 0.5393258426966292,
+      "grad_norm": 1.9416624949175059,
+      "learning_rate": 9.817027128840462e-06,
+      "loss": 0.3243,
+      "step": 120
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 1.6337659318383317,
+      "learning_rate": 9.740559296244543e-06,
+      "loss": 0.2935,
+      "step": 130
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 1.640309426588963,
+      "learning_rate": 9.651184092990109e-06,
+      "loss": 0.2785,
+      "step": 140
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 1.5558520954340391,
+      "learning_rate": 9.5491448656538e-06,
+      "loss": 0.2888,
+      "step": 150
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "eval_loss": 0.2572707235813141,
+      "eval_runtime": 17.4846,
+      "eval_samples_per_second": 21.447,
+      "eval_steps_per_second": 2.688,
+      "step": 150
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 1.433158612944013,
+      "learning_rate": 9.434719441818106e-06,
+      "loss": 0.2505,
+      "step": 160
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 1.6223270656786584,
+      "learning_rate": 9.308219373615574e-06,
+      "loss": 0.2499,
+      "step": 170
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 1.416660460405866,
+      "learning_rate": 9.16998908944939e-06,
+      "loss": 0.2488,
+      "step": 180
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 1.5181966540698182,
+      "learning_rate": 9.020404956200016e-06,
+      "loss": 0.2431,
+      "step": 190
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 1.529711085176287,
+      "learning_rate": 8.85987425447124e-06,
+      "loss": 0.246,
+      "step": 200
+    },
+    {
+      "epoch": 0.898876404494382,
+      "eval_loss": 0.21981053054332733,
+      "eval_runtime": 17.457,
+      "eval_samples_per_second": 21.481,
+      "eval_steps_per_second": 2.692,
+      "step": 200
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 1.2452657690009934,
+      "learning_rate": 8.688834069665819e-06,
+      "loss": 0.2246,
+      "step": 210
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 1.550856364479674,
+      "learning_rate": 8.50775010191001e-06,
+      "loss": 0.2306,
+      "step": 220
+    },
+    {
+      "epoch": 1.0314606741573034,
+      "grad_norm": 1.3059549606481422,
+      "learning_rate": 8.317115398067289e-06,
+      "loss": 0.1756,
+      "step": 230
+    },
+    {
+      "epoch": 1.0764044943820226,
+      "grad_norm": 1.2969411321364979,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 0.1532,
+      "step": 240
+    },
+    {
+      "epoch": 1.1213483146067416,
+      "grad_norm": 1.2587937924386081,
+      "learning_rate": 7.909294577789765e-06,
+      "loss": 0.1473,
+      "step": 250
+    },
+    {
+      "epoch": 1.1213483146067416,
+      "eval_loss": 0.21036630868911743,
+      "eval_runtime": 17.3756,
+      "eval_samples_per_second": 21.582,
+      "eval_steps_per_second": 2.705,
+      "step": 250
+    },
+    {
+      "epoch": 1.1662921348314608,
+      "grad_norm": 1.1553413221078348,
+      "learning_rate": 7.693218856597515e-06,
+      "loss": 0.1475,
+      "step": 260
+    },
+    {
+      "epoch": 1.2112359550561798,
+      "grad_norm": 1.3216911542659089,
+      "learning_rate": 7.469810166471802e-06,
+      "loss": 0.1483,
+      "step": 270
+    },
+    {
+      "epoch": 1.256179775280899,
+      "grad_norm": 1.1664826400709642,
+      "learning_rate": 7.239676794028526e-06,
+      "loss": 0.1511,
+      "step": 280
+    },
+    {
+      "epoch": 1.301123595505618,
+      "grad_norm": 1.5952719865840357,
+      "learning_rate": 7.003445335530572e-06,
+      "loss": 0.1419,
+      "step": 290
+    },
+    {
+      "epoch": 1.346067415730337,
+      "grad_norm": 1.0870131820519873,
+      "learning_rate": 6.761758990821143e-06,
+      "loss": 0.1449,
+      "step": 300
+    },
+    {
+      "epoch": 1.346067415730337,
+      "eval_loss": 0.19717492163181305,
+      "eval_runtime": 17.3905,
+      "eval_samples_per_second": 21.563,
+      "eval_steps_per_second": 2.703,
+      "step": 300
+    },
+    {
+      "epoch": 1.3910112359550562,
+      "grad_norm": 1.4154602546015522,
+      "learning_rate": 6.515275812049644e-06,
+      "loss": 0.1463,
+      "step": 310
+    },
+    {
+      "epoch": 1.4359550561797754,
+      "grad_norm": 1.1709528458456968,
+      "learning_rate": 6.264666911958404e-06,
+      "loss": 0.1405,
+      "step": 320
+    },
+    {
+      "epoch": 1.4808988764044944,
+      "grad_norm": 1.136245803763801,
+      "learning_rate": 6.0106146366086514e-06,
+      "loss": 0.1433,
+      "step": 330
+    },
+    {
+      "epoch": 1.5258426966292133,
+      "grad_norm": 1.2205607295411152,
+      "learning_rate": 5.753810707520918e-06,
+      "loss": 0.1403,
+      "step": 340
+    },
+    {
+      "epoch": 1.5707865168539326,
+      "grad_norm": 1.1459618622523857,
+      "learning_rate": 5.494954338288404e-06,
+      "loss": 0.1318,
+      "step": 350
+    },
+    {
+      "epoch": 1.5707865168539326,
+      "eval_loss": 0.18746493756771088,
+      "eval_runtime": 17.4259,
+      "eval_samples_per_second": 21.52,
+      "eval_steps_per_second": 2.697,
+      "step": 350
+    },
+    {
+      "epoch": 1.6157303370786518,
+      "grad_norm": 1.1081127136052973,
+      "learning_rate": 5.234750330791268e-06,
+      "loss": 0.1347,
+      "step": 360
+    },
+    {
+      "epoch": 1.6606741573033708,
+      "grad_norm": 1.2096824671699806,
+      "learning_rate": 4.973907156195405e-06,
+      "loss": 0.1371,
+      "step": 370
+    },
+    {
+      "epoch": 1.7056179775280897,
+      "grad_norm": 0.9321578295718935,
+      "learning_rate": 4.713135025960652e-06,
+      "loss": 0.1349,
+      "step": 380
+    },
+    {
+      "epoch": 1.750561797752809,
+      "grad_norm": 1.0032260480451698,
+      "learning_rate": 4.4531439581106295e-06,
+      "loss": 0.1405,
+      "step": 390
+    },
+    {
+      "epoch": 1.7955056179775282,
+      "grad_norm": 1.1088136668010249,
+      "learning_rate": 4.194641844029227e-06,
+      "loss": 0.1304,
+      "step": 400
+    },
+    {
+      "epoch": 1.7955056179775282,
+      "eval_loss": 0.17997325956821442,
+      "eval_runtime": 17.3876,
+      "eval_samples_per_second": 21.567,
+      "eval_steps_per_second": 2.703,
+      "step": 400
+    },
+    {
+      "epoch": 1.8404494382022472,
+      "grad_norm": 1.0635306305601684,
+      "learning_rate": 3.938332521047434e-06,
+      "loss": 0.1346,
+      "step": 410
+    },
+    {
+      "epoch": 1.8853932584269661,
+      "grad_norm": 1.218631723508059,
+      "learning_rate": 3.6849138560683305e-06,
+      "loss": 0.1234,
+      "step": 420
+    },
+    {
+      "epoch": 1.9303370786516854,
+      "grad_norm": 1.2698442806527548,
+      "learning_rate": 3.435075845448105e-06,
+      "loss": 0.1222,
+      "step": 430
+    },
+    {
+      "epoch": 1.9752808988764046,
+      "grad_norm": 1.1321670993981952,
+      "learning_rate": 3.189498736306584e-06,
+      "loss": 0.1322,
+      "step": 440
+    },
+    {
+      "epoch": 2.0179775280898875,
+      "grad_norm": 0.9501899019089498,
+      "learning_rate": 2.948851174382565e-06,
+      "loss": 0.1033,
+      "step": 450
+    },
+    {
+      "epoch": 2.0179775280898875,
+      "eval_loss": 0.173874631524086,
+      "eval_runtime": 17.4581,
+      "eval_samples_per_second": 21.48,
+      "eval_steps_per_second": 2.692,
+      "step": 450
+    },
+    {
+      "epoch": 2.0629213483146067,
+      "grad_norm": 1.1901338231062175,
+      "learning_rate": 2.7137883834768076e-06,
+      "loss": 0.065,
+      "step": 460
+    },
+    {
+      "epoch": 2.107865168539326,
+      "grad_norm": 1.2213175036794364,
+      "learning_rate": 2.4849503814396624e-06,
+      "loss": 0.0664,
+      "step": 470
+    },
+    {
+      "epoch": 2.152808988764045,
+      "grad_norm": 1.1153475829189523,
+      "learning_rate": 2.2629602375607373e-06,
+      "loss": 0.0584,
+      "step": 480
+    },
+    {
+      "epoch": 2.197752808988764,
+      "grad_norm": 1.098894377077785,
+      "learning_rate": 2.048422376105299e-06,
+      "loss": 0.0603,
+      "step": 490
+    },
+    {
+      "epoch": 2.242696629213483,
+      "grad_norm": 0.9585577902954808,
+      "learning_rate": 1.8419209306164653e-06,
+      "loss": 0.0555,
+      "step": 500
+    },
+    {
+      "epoch": 2.242696629213483,
+      "eval_loss": 0.19535784423351288,
+      "eval_runtime": 18.0495,
+      "eval_samples_per_second": 20.776,
+      "eval_steps_per_second": 2.604,
+      "step": 500
+    },
+    {
+      "epoch": 2.2876404494382023,
+      "grad_norm": 1.0960519732589205,
+      "learning_rate": 1.6440181534640277e-06,
+      "loss": 0.0554,
+      "step": 510
+    },
+    {
+      "epoch": 2.3325842696629215,
+      "grad_norm": 0.9474666508755432,
+      "learning_rate": 1.4552528849702852e-06,
+      "loss": 0.0608,
+      "step": 520
+    },
+    {
+      "epoch": 2.3775280898876403,
+      "grad_norm": 0.9808135071779055,
+      "learning_rate": 1.2761390862810907e-06,
+      "loss": 0.061,
+      "step": 530
+    },
+    {
+      "epoch": 2.4224719101123595,
+      "grad_norm": 1.0910926188238508,
+      "learning_rate": 1.107164439976764e-06,
+      "loss": 0.0601,
+      "step": 540
+    },
+    {
+      "epoch": 2.4674157303370787,
+      "grad_norm": 0.9740196750041777,
+      "learning_rate": 9.487890222330137e-07,
+      "loss": 0.059,
+      "step": 550
+    },
+    {
+      "epoch": 2.4674157303370787,
+      "eval_loss": 0.1922154724597931,
+      "eval_runtime": 17.4168,
+      "eval_samples_per_second": 21.531,
+      "eval_steps_per_second": 2.699,
+      "step": 550
+    },
+    {
+      "epoch": 2.512359550561798,
+      "grad_norm": 1.0277254632714419,
+      "learning_rate": 8.014440501472909e-07,
+      "loss": 0.0545,
+      "step": 560
+    },
+    {
+      "epoch": 2.5573033707865167,
+      "grad_norm": 1.0349003308944513,
+      "learning_rate": 6.655307076412637e-07,
+      "loss": 0.0627,
+      "step": 570
+    },
+    {
+      "epoch": 2.602247191011236,
+      "grad_norm": 1.2388527398235702,
+      "learning_rate": 5.414190531362162e-07,
+      "loss": 0.0609,
+      "step": 580
+    },
+    {
+      "epoch": 2.647191011235955,
+      "grad_norm": 1.02149421662929,
+      "learning_rate": 4.29447011975474e-07,
+      "loss": 0.0516,
+      "step": 590
+    },
+    {
+      "epoch": 2.692134831460674,
+      "grad_norm": 0.8792574350721681,
+      "learning_rate": 3.299194563372604e-07,
+      "loss": 0.0581,
+      "step": 600
+    },
+    {
+      "epoch": 2.692134831460674,
+      "eval_loss": 0.19437935948371887,
+      "eval_runtime": 17.6556,
+      "eval_samples_per_second": 21.24,
+      "eval_steps_per_second": 2.662,
+      "step": 600
+    },
+    {
+      "epoch": 2.737078651685393,
+      "grad_norm": 1.191263615677693,
+      "learning_rate": 2.431073751431529e-07,
+      "loss": 0.0573,
+      "step": 610
+    },
+    {
+      "epoch": 2.7820224719101123,
+      "grad_norm": 1.0048433806261339,
+      "learning_rate": 1.6924713622225975e-07,
+      "loss": 0.0494,
+      "step": 620
+    },
+    {
+      "epoch": 2.8269662921348315,
+      "grad_norm": 1.0583767642730464,
+      "learning_rate": 1.0853984274007246e-07,
+      "loss": 0.0528,
+      "step": 630
+    },
+    {
+      "epoch": 2.8719101123595507,
+      "grad_norm": 0.9685960900233866,
+      "learning_rate": 6.115078564427946e-08,
+      "loss": 0.0549,
+      "step": 640
+    },
+    {
+      "epoch": 2.9168539325842695,
+      "grad_norm": 1.1062660438754317,
+      "learning_rate": 2.7208993618390578e-08,
+      "loss": 0.0616,
+      "step": 650
+    },
+    {
+      "epoch": 2.9168539325842695,
+      "eval_loss": 0.19488400220870972,
+      "eval_runtime": 17.9753,
+      "eval_samples_per_second": 20.862,
+      "eval_steps_per_second": 2.615,
+      "step": 650
+    },
+    {
+      "epoch": 2.9617977528089887,
+      "grad_norm": 1.2067693229296945,
+      "learning_rate": 6.806881768539053e-09,
+      "loss": 0.0499,
+      "step": 660
+    },
+    {
+      "epoch": 3.0,
+      "step": 669,
+      "total_flos": 75789046251520.0,
+      "train_loss": 0.2089029460120807,
+      "train_runtime": 4570.3932,
+      "train_samples_per_second": 4.674,
+      "train_steps_per_second": 0.146
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 75789046251520.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

qwen3-8b-os-plan-124/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8f20218242756ed6582dc9fc5f16d22229eea1c268f5e7cffd0a22dc09bf172
+size 8145